AI Frankly
by AI Frankly
Latest episode
The Local Jarvis 3 Recipes for a Voice Assistant That Doesn't Have…
The Local Jarvis 3 Recipes for a Voice Assistant That Doesn't Have…
About this podcast
Playing with AI tools and sharing what happens. What worked, what broke, and what I learned. Executive Producer: NotebookLM. No hype. Just receipts.
aifrankly.substack.com
Episodes
- The Local Jarvis 3 Recipes for a Voice Assistant That Doesn't Have to Phone Home (Full Deep Dive) · 49 minA note before you listen: this episode's deep dive was produced in NotebookLM. NotebookLM is our executive producer. It also mispronounces Ollama as "Alama" about forty times. We…
- MCP 202: The Missing Control Layer (Full Deep Dive) · 60 minMCP 202: The Missing Control Layer Between Your Agents and Your Tools. Security researchers have a name for what's happening inside most enterprise AI deployments right now…
- The Week Anthropic Leaked. The Internet Met an Owl. · 52 min · Episode 17Half a million lines of source code leaked. A federal court fight the same week. And the thing the internet actually remembered was an ASCII owl named Zornix. This episode covers…
- The Blueprints Are Public Now | Anthropic, the Pentagon, and the Source Code That Changed Everything (Full Deep Dive) · 42 minAnthropic refused defense contract terms that would have allowed military use of Claude. A federal judge called the Pentagon's response classic First Amendment retaliation. Seven…
- Anthropic Did It Again | The Claude Code Source Leak (Full Deep Dive) · 46 min · Episode 15On March 31, 2026, an intern at a blockchain security firm checked the npm registry for the newest release of Claude Code. Within 30 seconds he found a 59.8MB source map file…
- I Thought March Was Over. Then Anthropic Shipped Claude Computer.(Full Deep Dive) · 38 min · Season 1 Episode 14Anthropic shipped six major products in March 2026. A federal lawsuit over autonomous weapons. And a quietly revised safety pledge with no hard stop. All in the same 30 days. In…
- Anthropic Didn't Get Hacked. It Still Had a Security Problem. (Full Deep Dive) · 45 minNobody hacked Anthropic. A misconfigured CMS left roughly 3,000 unpublished assets publicly accessible. One described a new model nobody was supposed to see yet. Cybersecurity…
- MCP 201: The Governance Deficit (Full Deep Dive) · 40 min · Season 1 Episode 12MCP hit 30 CVEs in 60 days. 38 percent of public MCP servers had zero authentication. The protocol works. The governance layer doesn't exist yet. This episode covers the real…
- This Already Hit Production. Your Policy Isn't Ready. (Full Deep Dive) · 33 min · Season 1Bonus Episode - Season 1 Anthropic didn't have a week. They had a product conference that nobody announced. This deep dive breaks down everything that shipped in March 2026…
- MCP 103: I Gave Claude Code Someone Else's Tools (Full Deep Dive) · 37 minHere are the show notes: MCP 103: I Gave Claude Code Someone Else's Tools (Full Deep Dive) Season 1, Episode 11 This week I wired three public MCP servers into Claude Code and…
- MCP 102: Claude Already Knows (Full Deep Dive) · 24 min · Season 1 Episode 7Here are the show notes: MCP 101 was the spec. MCP 102 is the behavior. In this episode we go beyond the documentation. We cover what actually happens when you flip the switch…
- MCP 101: I Read the Documentation So You Don't Have To (Full Deep Dive) · 35 minEveryone is making videos about MCP. Nobody is reading the actual documentation. This is the full 35-minute deep dive on the Model Context Protocol, grounded entirely in official…
- Your Boss Just Saw What Goldman Did With AI (Full Deep Dive) · 38 minThe full deep dive podcast on the Goldman Sachs x Anthropic story. What we cover: The $285 billion software sell-off and what triggered it. What Goldman actually built with…
- The full deep dive. Two parts, one episode. · 34 min · Season 1 Episode 5The full deep dive. Two parts, one episode. Part 1 explored the plumbing behind Visa's AI agents and why 4,700% bot traffic is the reason we can't have nice things yet. Part 2…
- The Clean Room Method · 40 minYour prompt is a suggestion. Your source is gospel. This week we break down the Clean Room Method, a 5-step framework to stop AI tools from leaking your personal information…
- Local Does Not Equal Safe · 22 minYour local AI agent has system access, reads untrusted input, and can send data out. That's the Lethal Trifecta. In this episode we dissect a case study from early 2026 and…
- Karma as Code: The Rise of the Persistent RPG · 31 minWhat if your next RPG remembered everything? Not just this playthrough. Every playthrough. Every choice. Every betrayal. Across every game in the franchise. AI agent swarms are…
- The Fifth Party Problem: Who Pays When AI Agents Go Rogue · 34 minWho pays when your AI agent books the wrong flight? This episode combines two articles originally published on AI Frankly: Part 1: "The Plumbing Behind the Hype" (December 19…
- Fear is Fake: Why You're Still Not Running Local AI · 32 minThe barrier isn't Python. It isn't hardware. It's the fear of breaking something that has a 30-second fix. In this episode: - The 3 Fake Fears (Daily Driver, Rabbit Hole, No…
- The Nuclear Option: How I Turned My Gaming Rig Into a Sovereign AI Server · 34 min · Season 1 Episode 1I repurposed my gaming rig into a local AI server with zero cloud dependency. In this deep dive, we break down why I stopped trusting managed AI services, how to set up LM Studio…
